AI Context Operations Lead

Mercury•Portland, OR

1d•$146,700 - $203,800

About The Position

Mercury is building a whole stack of financial tools for startups. AI Ops builds the systems that keep that organization moving, helping teams move quickly without losing shared context. In this role, you'll own Mercury's internal knowledge infrastructure: the systems and standards that make company information accurate, discoverable, and useful. You'll build and maintain a trusted context layer—a structured, living record of what teams own, are building, and know—and ensure it stays current automatically. That context layer powers leadership reporting, planning, operational reviews, and the internal AI agents employees use every day. You'll define how information is organized, validated, and maintained across systems like Linear and Mercury's internal platforms so they function as a single source of truth. Working closely with Engineering, who own the underlying infrastructure, you'll design the knowledge layer above it: the taxonomies, schemas, validation workflows, and automations that make company knowledge reliable for both people and AI systems. This role sits at the intersection of systems operations, knowledge architecture, and product thinking. Success isn't measured by collecting more information, but by creating a high-signal knowledge system that helps employees find answers quickly, enables leaders to make decisions from shared context, and gives AI systems the foundation they need to operate effectively. Mercury aims to make banking feel secure, reliable, thoughtful, and perhaps even magical. Your job is to make the company's internal knowledge systems just as dependable.

Requirements

5–8 years of experience in program or product operations, technical program management, product management, data, or similar roles where you drove company-wide systems or operational improvements.
Think like a systems designer and knowledge architect, able to turn messy, distributed information into simple, scalable structures that people and AI systems can easily understand and trust.
Be comfortable working with technical systems, including APIs, data models, analytics, and tools like Linear, GitHub, Metabase, and modern AI platforms, even if you aren't building the underlying infrastructure yourself.
Have hands-on experience using AI to create leverage through workflows, automations, agents, or other practical applications, along with a solid understanding of how LLMs retrieve and consume information.
Influence organizations through strong judgment, clear communication, and thoughtful execution, thriving in ambiguous environments where the right systems have to be invented rather than inherited.

Responsibilities

Own Mercury's knowledge infrastructure: the trusted context layer that captures what every team owns, is building, and knows, along with the information architecture, taxonomy, and governance that keep it accurate, current, and useful.
Build the knowledge layer on top of Mercury's AI infrastructure by partnering with AI Engineering to design the schemas, automations, and validation workflows that allow people and AI agents to reliably retrieve and act on company knowledge.
Own the reporting layer that turns shared context into operational insight, including leadership reporting, roadmap views, planning dashboards, and the reporting that powers company operating cadences.
Drive company-wide adoption of standardized systems and practices by partnering across Engineering, Product, Design, Data, Compliance, Legal, Finance, Partnerships, Customer Support, and other teams to replace fragmented documentation with trusted, structured sources of truth.
Continuously improve how Mercury captures, organizes, and uses knowledge by identifying operational friction, building better workflows, and ensuring employees have the tooling and enablement they need to effectively work with AI.